Commit a0e60b20 authored by David Gibson's avatar David Gibson Committed by Paul Mackerras

[PATCH] powerpc: Merge bitops.h

Here's a revised version.  This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch).  In fact it is used in the powermac interrupt code
(but not on pSeries).

- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
  instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S

- ppc32 previously used a full "sync" barrier at the end of
  test_and_*_bit(), whereas ppc64 used an "isync".  The merged version
  uses "isync", since I believe that's sufficient.

- The ppc64 versions of then minix_*() bitmap functions have changed
  semantics.  Previously on ppc64, these functions were big-endian
  (that is bit 0 was the LSB in the first 64-bit, big-endian word).
  On ppc32 (and x86, for that matter, they were little-endian.  As far
  as I can tell, the big-endian usage was simply wrong - I guess
  no-one ever tried to use minixfs on ppc64.

- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
  inline (they were already out-of-line on ppc64).

- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
  the merged bitops.  What it was doing in mmu_context.h in the first
  place, I have no idea.

- The fls() function is now implemented using the cntlzw instruction
  on ppc64, instead of generic_fls(), as it already was on ppc32.

- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
  arch/ppc/Makefile.  This in turn requires some changes to
  arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.

Built and running on G5.
Signed-off-by: default avatarDavid Gibson <david@gibson.dropbear.id.au>
Signed-off-by: default avatarPaul Mackerras <paulus@samba.org>
parent 031ef0a7
...@@ -81,15 +81,6 @@ EXPORT_SYMBOL(_prep_type); ...@@ -81,15 +81,6 @@ EXPORT_SYMBOL(_prep_type);
EXPORT_SYMBOL(ucSystemType); EXPORT_SYMBOL(ucSystemType);
#endif #endif
#if !defined(__INLINE_BITOPS)
EXPORT_SYMBOL(set_bit);
EXPORT_SYMBOL(clear_bit);
EXPORT_SYMBOL(change_bit);
EXPORT_SYMBOL(test_and_set_bit);
EXPORT_SYMBOL(test_and_clear_bit);
EXPORT_SYMBOL(test_and_change_bit);
#endif /* __INLINE_BITOPS */
EXPORT_SYMBOL(strcpy); EXPORT_SYMBOL(strcpy);
EXPORT_SYMBOL(strncpy); EXPORT_SYMBOL(strncpy);
EXPORT_SYMBOL(strcat); EXPORT_SYMBOL(strcat);
......
...@@ -3,13 +3,14 @@ ...@@ -3,13 +3,14 @@
# #
ifeq ($(CONFIG_PPC_MERGE),y) ifeq ($(CONFIG_PPC_MERGE),y)
obj-y := string.o obj-y := string.o strcase.o
obj-$(CONFIG_PPC32) += div64.o copy_32.o checksum_32.o
endif endif
obj-y += strcase.o obj-y += bitops.o
obj-$(CONFIG_PPC32) += div64.o copy_32.o checksum_32.o
obj-$(CONFIG_PPC64) += checksum_64.o copypage_64.o copyuser_64.o \ obj-$(CONFIG_PPC64) += checksum_64.o copypage_64.o copyuser_64.o \
memcpy_64.o usercopy_64.o mem_64.o string.o memcpy_64.o usercopy_64.o mem_64.o string.o \
strcase.o
obj-$(CONFIG_PPC_ISERIES) += e2a.o obj-$(CONFIG_PPC_ISERIES) += e2a.o
obj-$(CONFIG_XMON) += sstep.o obj-$(CONFIG_XMON) += sstep.o
......
/* #include <linux/types.h>
* These are too big to be inlined.
*/
#include <linux/kernel.h>
#include <linux/module.h> #include <linux/module.h>
#include <linux/bitops.h>
#include <asm/byteorder.h> #include <asm/byteorder.h>
#include <asm/bitops.h>
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, /**
* find_next_bit - find the next set bit in a memory region
* @addr: The address to base the search on
* @offset: The bitnumber to start searching at
* @size: The maximum size to search
*/
unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
unsigned long offset) unsigned long offset)
{ {
const unsigned long *p = addr + (offset >> 6); const unsigned long *p = addr + BITOP_WORD(offset);
unsigned long result = offset & ~63UL; unsigned long result = offset & ~(BITS_PER_LONG-1);
unsigned long tmp; unsigned long tmp;
if (offset >= size) if (offset >= size)
return size; return size;
size -= result; size -= result;
offset &= 63UL; offset %= BITS_PER_LONG;
if (offset) { if (offset) {
tmp = *(p++); tmp = *(p++);
tmp |= ~0UL >> (64 - offset); tmp &= (~0UL << offset);
if (size < 64) if (size < BITS_PER_LONG)
goto found_first; goto found_first;
if (~tmp) if (tmp)
goto found_middle; goto found_middle;
size -= 64; size -= BITS_PER_LONG;
result += 64; result += BITS_PER_LONG;
} }
while (size & ~63UL) { while (size & ~(BITS_PER_LONG-1)) {
if (~(tmp = *(p++))) if ((tmp = *(p++)))
goto found_middle; goto found_middle;
result += 64; result += BITS_PER_LONG;
size -= 64; size -= BITS_PER_LONG;
} }
if (!size) if (!size)
return result; return result;
tmp = *p; tmp = *p;
found_first: found_first:
tmp |= ~0UL << size; tmp &= (~0UL >> (64 - size));
if (tmp == ~0UL) /* Are any bits zero? */ if (tmp == 0UL) /* Are any bits set? */
return result + size; /* Nope. */ return result + size; /* Nope. */
found_middle: found_middle:
return result + ffz(tmp); return result + __ffs(tmp);
} }
EXPORT_SYMBOL(find_next_bit);
EXPORT_SYMBOL(find_next_zero_bit); /*
* This implementation of find_{first,next}_zero_bit was stolen from
unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * Linus' asm-alpha/bitops.h.
*/
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
unsigned long offset) unsigned long offset)
{ {
const unsigned long *p = addr + (offset >> 6); const unsigned long *p = addr + BITOP_WORD(offset);
unsigned long result = offset & ~63UL; unsigned long result = offset & ~(BITS_PER_LONG-1);
unsigned long tmp; unsigned long tmp;
if (offset >= size) if (offset >= size)
return size; return size;
size -= result; size -= result;
offset &= 63UL; offset %= BITS_PER_LONG;
if (offset) { if (offset) {
tmp = *(p++); tmp = *(p++);
tmp &= (~0UL << offset); tmp |= ~0UL >> (BITS_PER_LONG - offset);
if (size < 64) if (size < BITS_PER_LONG)
goto found_first; goto found_first;
if (tmp) if (~tmp)
goto found_middle; goto found_middle;
size -= 64; size -= BITS_PER_LONG;
result += 64; result += BITS_PER_LONG;
} }
while (size & ~63UL) { while (size & ~(BITS_PER_LONG-1)) {
if ((tmp = *(p++))) if (~(tmp = *(p++)))
goto found_middle; goto found_middle;
result += 64; result += BITS_PER_LONG;
size -= 64; size -= BITS_PER_LONG;
} }
if (!size) if (!size)
return result; return result;
tmp = *p; tmp = *p;
found_first: found_first:
tmp &= (~0UL >> (64 - size)); tmp |= ~0UL << size;
if (tmp == 0UL) /* Are any bits set? */ if (tmp == ~0UL) /* Are any bits zero? */
return result + size; /* Nope. */ return result + size; /* Nope. */
found_middle: found_middle:
return result + __ffs(tmp); return result + ffz(tmp);
} }
EXPORT_SYMBOL(find_next_zero_bit);
EXPORT_SYMBOL(find_next_bit);
static inline unsigned int ext2_ilog2(unsigned int x) static inline unsigned int ext2_ilog2(unsigned int x)
{ {
...@@ -106,8 +110,8 @@ static inline unsigned int ext2_ffz(unsigned int x) ...@@ -106,8 +110,8 @@ static inline unsigned int ext2_ffz(unsigned int x)
return rc; return rc;
} }
unsigned long find_next_zero_le_bit(const unsigned long *addr, unsigned long size, unsigned long find_next_zero_le_bit(const unsigned long *addr,
unsigned long offset) unsigned long size, unsigned long offset)
{ {
const unsigned int *p = ((const unsigned int *)addr) + (offset >> 5); const unsigned int *p = ((const unsigned int *)addr) + (offset >> 5);
unsigned int result = offset & ~31; unsigned int result = offset & ~31;
...@@ -143,5 +147,4 @@ found_first: ...@@ -143,5 +147,4 @@ found_first:
found_middle: found_middle:
return result + ext2_ffz(tmp); return result + ext2_ffz(tmp);
} }
EXPORT_SYMBOL(find_next_zero_le_bit); EXPORT_SYMBOL(find_next_zero_le_bit);
...@@ -66,7 +66,8 @@ head-$(CONFIG_PPC_FPU) += arch/powerpc/kernel/fpu.o ...@@ -66,7 +66,8 @@ head-$(CONFIG_PPC_FPU) += arch/powerpc/kernel/fpu.o
core-y += arch/ppc/kernel/ arch/powerpc/kernel/ \ core-y += arch/ppc/kernel/ arch/powerpc/kernel/ \
arch/ppc/platforms/ \ arch/ppc/platforms/ \
arch/ppc/mm/ arch/ppc/lib/ \ arch/ppc/mm/ arch/ppc/lib/ \
arch/ppc/syslib/ arch/powerpc/sysdev/ arch/ppc/syslib/ arch/powerpc/sysdev/ \
arch/powerpc/lib/
core-$(CONFIG_4xx) += arch/ppc/platforms/4xx/ core-$(CONFIG_4xx) += arch/ppc/platforms/4xx/
core-$(CONFIG_83xx) += arch/ppc/platforms/83xx/ core-$(CONFIG_83xx) += arch/ppc/platforms/83xx/
core-$(CONFIG_85xx) += arch/ppc/platforms/85xx/ core-$(CONFIG_85xx) += arch/ppc/platforms/85xx/
......
/*
* Copyright (C) 1996 Paul Mackerras.
*/
#include <linux/kernel.h>
#include <linux/bitops.h>
/*
* If the bitops are not inlined in bitops.h, they are defined here.
* -- paulus
*/
#if !__INLINE_BITOPS
void set_bit(int nr, volatile void * addr)
{
unsigned long old;
unsigned long mask = 1 << (nr & 0x1f);
unsigned long *p = ((unsigned long *)addr) + (nr >> 5);
__asm__ __volatile__(SMP_WMB "\n\
1: lwarx %0,0,%3 \n\
or %0,%0,%2 \n"
PPC405_ERR77(0,%3)
" stwcx. %0,0,%3 \n\
bne 1b"
SMP_MB
: "=&r" (old), "=m" (*p)
: "r" (mask), "r" (p), "m" (*p)
: "cc" );
}
void clear_bit(int nr, volatile void *addr)
{
unsigned long old;
unsigned long mask = 1 << (nr & 0x1f);
unsigned long *p = ((unsigned long *)addr) + (nr >> 5);
__asm__ __volatile__(SMP_WMB "\n\
1: lwarx %0,0,%3 \n\
andc %0,%0,%2 \n"
PPC405_ERR77(0,%3)
" stwcx. %0,0,%3 \n\
bne 1b"
SMP_MB
: "=&r" (old), "=m" (*p)
: "r" (mask), "r" (p), "m" (*p)
: "cc");
}
void change_bit(int nr, volatile void *addr)
{
unsigned long old;
unsigned long mask = 1 << (nr & 0x1f);
unsigned long *p = ((unsigned long *)addr) + (nr >> 5);
__asm__ __volatile__(SMP_WMB "\n\
1: lwarx %0,0,%3 \n\
xor %0,%0,%2 \n"
PPC405_ERR77(0,%3)
" stwcx. %0,0,%3 \n\
bne 1b"
SMP_MB
: "=&r" (old), "=m" (*p)
: "r" (mask), "r" (p), "m" (*p)
: "cc");
}
int test_and_set_bit(int nr, volatile void *addr)
{
unsigned int old, t;
unsigned int mask = 1 << (nr & 0x1f);
volatile unsigned int *p = ((volatile unsigned int *)addr) + (nr >> 5);
__asm__ __volatile__(SMP_WMB "\n\
1: lwarx %0,0,%4 \n\
or %1,%0,%3 \n"
PPC405_ERR77(0,%4)
" stwcx. %1,0,%4 \n\
bne 1b"
SMP_MB
: "=&r" (old), "=&r" (t), "=m" (*p)
: "r" (mask), "r" (p), "m" (*p)
: "cc");
return (old & mask) != 0;
}
int test_and_clear_bit(int nr, volatile void *addr)
{
unsigned int old, t;
unsigned int mask = 1 << (nr & 0x1f);
volatile unsigned int *p = ((volatile unsigned int *)addr) + (nr >> 5);
__asm__ __volatile__(SMP_WMB "\n\
1: lwarx %0,0,%4 \n\
andc %1,%0,%3 \n"
PPC405_ERR77(0,%4)
" stwcx. %1,0,%4 \n\
bne 1b"
SMP_MB
: "=&r" (old), "=&r" (t), "=m" (*p)
: "r" (mask), "r" (p), "m" (*p)
: "cc");
return (old & mask) != 0;
}
int test_and_change_bit(int nr, volatile void *addr)
{
unsigned int old, t;
unsigned int mask = 1 << (nr & 0x1f);
volatile unsigned int *p = ((volatile unsigned int *)addr) + (nr >> 5);
__asm__ __volatile__(SMP_WMB "\n\
1: lwarx %0,0,%4 \n\
xor %1,%0,%3 \n"
PPC405_ERR77(0,%4)
" stwcx. %1,0,%4 \n\
bne 1b"
SMP_MB
: "=&r" (old), "=&r" (t), "=m" (*p)
: "r" (mask), "r" (p), "m" (*p)
: "cc");
return (old & mask) != 0;
}
#endif /* !__INLINE_BITOPS */
...@@ -13,7 +13,7 @@ endif ...@@ -13,7 +13,7 @@ endif
obj-y += irq.o idle.o dma.o \ obj-y += irq.o idle.o dma.o \
signal.o \ signal.o \
align.o bitops.o pacaData.o \ align.o pacaData.o \
udbg.o ioctl32.o \ udbg.o ioctl32.o \
rtc.o \ rtc.o \
cpu_setup_power4.o \ cpu_setup_power4.o \
......
This diff is collapsed.
...@@ -16,21 +16,6 @@ ...@@ -16,21 +16,6 @@
* 2 of the License, or (at your option) any later version. * 2 of the License, or (at your option) any later version.
*/ */
/*
* Every architecture must define this function. It's the fastest
* way of searching a 140-bit bitmap where the first 100 bits are
* unlikely to be set. It's guaranteed that at least one of the 140
* bits is cleared.
*/
static inline int sched_find_first_bit(unsigned long *b)
{
if (unlikely(b[0]))
return __ffs(b[0]);
if (unlikely(b[1]))
return __ffs(b[1]) + 64;
return __ffs(b[2]) + 128;
}
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{ {
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment